# MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition

arXiv: https://arxiv.org/abs/2212.00500 · HTML: https://mlsanity.com/paper/2212.00500/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [M6: A Chinese Multimodal Pretrainer](https://mlsanity.com/paper/2103.00823/) (2021)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [Unified Speech-Text Pre-training for Speech Translation and Recognition](https://mlsanity.com/paper/2204.05409/) (2022)
- [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://mlsanity.com/paper/2107.05782/) (2021)
- [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://mlsanity.com/paper/2010.11338/) (2020)
- [Learning Shared Semantic Space for Speech-to-Text Translation](https://mlsanity.com/paper/2105.03095/) (2021)
- [Transformers with convolutional context for ASR](https://mlsanity.com/paper/1904.11660/) (2019)
- [SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training](https://mlsanity.com/paper/2210.03730/) (2022)
- [Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages](https://mlsanity.com/paper/2205.01086/) (2022)
- [Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data](https://mlsanity.com/paper/2203.17113/) (2022)

## Built on by (most cited first, 9 of 9)

- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities](https://mlsanity.com/paper/2305.11172/) (2023)
- [Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition](https://mlsanity.com/paper/2309.10294/) (2023)
- [An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement](https://mlsanity.com/paper/2402.17189/) (2024)
- [Mu2SLAM: Multitask, Multilingual Speech and Language Models](https://mlsanity.com/paper/2212.09553/) (2022)
- [Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation](https://mlsanity.com/paper/2310.14278/) (2023)
- [Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection](https://mlsanity.com/paper/2412.08651/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phoneme modality into pre-training, which can help capture modality-invariant information between Mandarin speech and text. Specifically, we employ a multi-task learning framework including five self-supervised and supervised tasks with speech and text data. For end-to-end pre-training, we introduce self-supervised speech-to-pseudo-codes (S2C) and phoneme-to-text (P2T) tasks utilizing unlabeled speech and text data, where speech-pseudo-codes pairs and phoneme-text pairs are a supplement to the supervised speech-text pairs. To train the encoder to learn better speech representation, we introduce self-supervised masked speech prediction (MSP) and supervised phoneme prediction (PP) tasks to learn to map speech into phonemes. Besides, we directly add the downstream supervised speech-to-text (S2T) task into the pre-training process, which can further improve the pre-training performance and achieve better recognition results even without fine-tuning. Experiments on AISHELL-1 show that our proposed method achieves state-of-the-art performance, with a more than 40% relative improvement compared with other pre-training methods.